© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94256
    Prev
    Next
    INDEX
    Explanations

    version and start sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Club
    -0.78
    finite
    -0.77
    rune
    -0.76
    pling
    -0.70
     Club
    -0.70
    agang
    -0.68
    continued
    -0.67
     maquiagem
    -0.67
    FT
    -0.66
    Resize
    -0.66
    POSITIVE LOGITS
     pianos
    0.77
     cyto
    0.76
    GIR
    0.73
    Monica
    0.73
     Monica
    0.73
    tanque
    0.71
     Cyto
    0.71
    设置为
    0.71
    心的
    0.69
    珥
    0.69
    Activations Density 0.086%

    No Known Activations